swardify-t5-base / checkpoint-777 /trainer_state.json
bricesuazo's picture
Upload folder using huggingface_hub
b385d34 verified
{
"best_metric": 3.1822056770324707,
"best_model_checkpoint": "swardify-t5-base/checkpoint-777",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 777,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.023166023166023165,
"grad_norm": NaN,
"learning_rate": 0.0,
"loss": 9.0761,
"step": 6
},
{
"epoch": 0.04633204633204633,
"grad_norm": 51.163658142089844,
"learning_rate": 3.846153846153847e-06,
"loss": 8.493,
"step": 12
},
{
"epoch": 0.0694980694980695,
"grad_norm": 34.79372787475586,
"learning_rate": 7.692307692307694e-06,
"loss": 9.1207,
"step": 18
},
{
"epoch": 0.09266409266409266,
"grad_norm": 29.063369750976562,
"learning_rate": 1.153846153846154e-05,
"loss": 6.2012,
"step": 24
},
{
"epoch": 0.11583011583011583,
"grad_norm": 108.47474670410156,
"learning_rate": 1.5384615384615387e-05,
"loss": 8.0014,
"step": 30
},
{
"epoch": 0.138996138996139,
"grad_norm": 40.11521911621094,
"learning_rate": 1.923076923076923e-05,
"loss": 6.7531,
"step": 36
},
{
"epoch": 0.16216216216216217,
"grad_norm": 21.81500244140625,
"learning_rate": 2.307692307692308e-05,
"loss": 6.1148,
"step": 42
},
{
"epoch": 0.18532818532818532,
"grad_norm": 118.32696533203125,
"learning_rate": 2.6923076923076923e-05,
"loss": 5.8517,
"step": 48
},
{
"epoch": 0.2084942084942085,
"grad_norm": 31.352462768554688,
"learning_rate": 3.0769230769230774e-05,
"loss": 6.7338,
"step": 54
},
{
"epoch": 0.23166023166023167,
"grad_norm": 50.72134017944336,
"learning_rate": 3.461538461538462e-05,
"loss": 6.1796,
"step": 60
},
{
"epoch": 0.2548262548262548,
"grad_norm": 12.974916458129883,
"learning_rate": 3.846153846153846e-05,
"loss": 5.5243,
"step": 66
},
{
"epoch": 0.277992277992278,
"grad_norm": 63.90497970581055,
"learning_rate": 4.230769230769231e-05,
"loss": 6.7863,
"step": 72
},
{
"epoch": 0.30115830115830117,
"grad_norm": 13.123330116271973,
"learning_rate": 4.5512820512820516e-05,
"loss": 4.2131,
"step": 78
},
{
"epoch": 0.32432432432432434,
"grad_norm": 27.849990844726562,
"learning_rate": 4.935897435897436e-05,
"loss": 6.5816,
"step": 84
},
{
"epoch": 0.3474903474903475,
"grad_norm": 69.52152252197266,
"learning_rate": 4.964234620886982e-05,
"loss": 6.1139,
"step": 90
},
{
"epoch": 0.37065637065637064,
"grad_norm": 30.392309188842773,
"learning_rate": 4.921316165951359e-05,
"loss": 5.971,
"step": 96
},
{
"epoch": 0.3938223938223938,
"grad_norm": 20.638032913208008,
"learning_rate": 4.878397711015737e-05,
"loss": 4.9646,
"step": 102
},
{
"epoch": 0.416988416988417,
"grad_norm": 21.338809967041016,
"learning_rate": 4.8354792560801146e-05,
"loss": 5.8206,
"step": 108
},
{
"epoch": 0.44015444015444016,
"grad_norm": 18.209985733032227,
"learning_rate": 4.792560801144492e-05,
"loss": 4.6264,
"step": 114
},
{
"epoch": 0.46332046332046334,
"grad_norm": 18.156341552734375,
"learning_rate": 4.74964234620887e-05,
"loss": 3.7616,
"step": 120
},
{
"epoch": 0.4864864864864865,
"grad_norm": 9.134263038635254,
"learning_rate": 4.7067238912732475e-05,
"loss": 3.9017,
"step": 126
},
{
"epoch": 0.5096525096525096,
"grad_norm": 11.322493553161621,
"learning_rate": 4.663805436337626e-05,
"loss": 4.5921,
"step": 132
},
{
"epoch": 0.5328185328185329,
"grad_norm": 20.7261905670166,
"learning_rate": 4.620886981402003e-05,
"loss": 4.4158,
"step": 138
},
{
"epoch": 0.555984555984556,
"grad_norm": 11.311534881591797,
"learning_rate": 4.577968526466381e-05,
"loss": 4.0813,
"step": 144
},
{
"epoch": 0.5791505791505791,
"grad_norm": 16.623924255371094,
"learning_rate": 4.5350500715307586e-05,
"loss": 4.7313,
"step": 150
},
{
"epoch": 0.6023166023166023,
"grad_norm": 15.561365127563477,
"learning_rate": 4.492131616595136e-05,
"loss": 3.9911,
"step": 156
},
{
"epoch": 0.6254826254826255,
"grad_norm": 15.34063720703125,
"learning_rate": 4.449213161659514e-05,
"loss": 4.8839,
"step": 162
},
{
"epoch": 0.6486486486486487,
"grad_norm": 17.363418579101562,
"learning_rate": 4.4062947067238915e-05,
"loss": 4.4482,
"step": 168
},
{
"epoch": 0.6718146718146718,
"grad_norm": 10.494095802307129,
"learning_rate": 4.363376251788269e-05,
"loss": 3.4289,
"step": 174
},
{
"epoch": 0.694980694980695,
"grad_norm": 13.092146873474121,
"learning_rate": 4.320457796852647e-05,
"loss": 3.826,
"step": 180
},
{
"epoch": 0.7181467181467182,
"grad_norm": 9.929197311401367,
"learning_rate": 4.2775393419170244e-05,
"loss": 4.997,
"step": 186
},
{
"epoch": 0.7413127413127413,
"grad_norm": 8.76804256439209,
"learning_rate": 4.234620886981403e-05,
"loss": 4.3643,
"step": 192
},
{
"epoch": 0.7644787644787645,
"grad_norm": 10.548382759094238,
"learning_rate": 4.1917024320457796e-05,
"loss": 3.9267,
"step": 198
},
{
"epoch": 0.7876447876447876,
"grad_norm": 12.139382362365723,
"learning_rate": 4.148783977110158e-05,
"loss": 3.9444,
"step": 204
},
{
"epoch": 0.8108108108108109,
"grad_norm": 8.579113960266113,
"learning_rate": 4.105865522174535e-05,
"loss": 3.578,
"step": 210
},
{
"epoch": 0.833976833976834,
"grad_norm": 11.02019214630127,
"learning_rate": 4.062947067238913e-05,
"loss": 4.0247,
"step": 216
},
{
"epoch": 0.8571428571428571,
"grad_norm": 29.3343505859375,
"learning_rate": 4.02002861230329e-05,
"loss": 3.4999,
"step": 222
},
{
"epoch": 0.8803088803088803,
"grad_norm": 8.917579650878906,
"learning_rate": 3.9771101573676684e-05,
"loss": 3.8837,
"step": 228
},
{
"epoch": 0.9034749034749034,
"grad_norm": 7.548088550567627,
"learning_rate": 3.9341917024320454e-05,
"loss": 3.847,
"step": 234
},
{
"epoch": 0.9266409266409267,
"grad_norm": 7.723937034606934,
"learning_rate": 3.891273247496424e-05,
"loss": 2.783,
"step": 240
},
{
"epoch": 0.9498069498069498,
"grad_norm": 19.019685745239258,
"learning_rate": 3.848354792560801e-05,
"loss": 3.9959,
"step": 246
},
{
"epoch": 0.972972972972973,
"grad_norm": 11.181546211242676,
"learning_rate": 3.805436337625179e-05,
"loss": 3.4081,
"step": 252
},
{
"epoch": 0.9961389961389961,
"grad_norm": 9.951409339904785,
"learning_rate": 3.7625178826895566e-05,
"loss": 3.4448,
"step": 258
},
{
"epoch": 1.0,
"eval_gen_len": 6.6154,
"eval_loss": 3.645592212677002,
"eval_rouge1": 9.7015,
"eval_rouge2": 5.6335,
"eval_rougeL": 9.3547,
"eval_rougeLsum": 9.5155,
"eval_runtime": 4.9627,
"eval_samples_per_second": 13.098,
"eval_steps_per_second": 3.426,
"step": 259
},
{
"epoch": 1.0193050193050193,
"grad_norm": 9.180315971374512,
"learning_rate": 3.719599427753934e-05,
"loss": 3.8576,
"step": 264
},
{
"epoch": 1.0424710424710424,
"grad_norm": 9.768823623657227,
"learning_rate": 3.676680972818312e-05,
"loss": 3.5363,
"step": 270
},
{
"epoch": 1.0656370656370657,
"grad_norm": 9.186162948608398,
"learning_rate": 3.6337625178826894e-05,
"loss": 2.9161,
"step": 276
},
{
"epoch": 1.0888030888030888,
"grad_norm": 5.980693817138672,
"learning_rate": 3.590844062947068e-05,
"loss": 3.8179,
"step": 282
},
{
"epoch": 1.111969111969112,
"grad_norm": 20.829463958740234,
"learning_rate": 3.5479256080114454e-05,
"loss": 2.6779,
"step": 288
},
{
"epoch": 1.135135135135135,
"grad_norm": 15.735648155212402,
"learning_rate": 3.505007153075823e-05,
"loss": 3.7684,
"step": 294
},
{
"epoch": 1.1583011583011582,
"grad_norm": 5.63276481628418,
"learning_rate": 3.4620886981402006e-05,
"loss": 2.7927,
"step": 300
},
{
"epoch": 1.1814671814671815,
"grad_norm": 5.006065845489502,
"learning_rate": 3.419170243204578e-05,
"loss": 2.8692,
"step": 306
},
{
"epoch": 1.2046332046332047,
"grad_norm": 10.745657920837402,
"learning_rate": 3.376251788268956e-05,
"loss": 3.1925,
"step": 312
},
{
"epoch": 1.2277992277992278,
"grad_norm": 11.546165466308594,
"learning_rate": 3.3333333333333335e-05,
"loss": 3.9131,
"step": 318
},
{
"epoch": 1.250965250965251,
"grad_norm": 7.276663780212402,
"learning_rate": 3.290414878397711e-05,
"loss": 3.6568,
"step": 324
},
{
"epoch": 1.2741312741312742,
"grad_norm": 4.786994457244873,
"learning_rate": 3.247496423462089e-05,
"loss": 3.5466,
"step": 330
},
{
"epoch": 1.2972972972972974,
"grad_norm": 11.583497047424316,
"learning_rate": 3.2045779685264664e-05,
"loss": 3.1339,
"step": 336
},
{
"epoch": 1.3204633204633205,
"grad_norm": 11.542532920837402,
"learning_rate": 3.161659513590845e-05,
"loss": 3.8298,
"step": 342
},
{
"epoch": 1.3436293436293436,
"grad_norm": 12.93191146850586,
"learning_rate": 3.1187410586552216e-05,
"loss": 2.9133,
"step": 348
},
{
"epoch": 1.3667953667953667,
"grad_norm": 10.973305702209473,
"learning_rate": 3.0758226037196e-05,
"loss": 3.9245,
"step": 354
},
{
"epoch": 1.3899613899613898,
"grad_norm": 8.375068664550781,
"learning_rate": 3.0329041487839772e-05,
"loss": 2.5798,
"step": 360
},
{
"epoch": 1.4131274131274132,
"grad_norm": 11.476892471313477,
"learning_rate": 2.9899856938483552e-05,
"loss": 2.5942,
"step": 366
},
{
"epoch": 1.4362934362934363,
"grad_norm": 11.129337310791016,
"learning_rate": 2.9470672389127325e-05,
"loss": 3.0223,
"step": 372
},
{
"epoch": 1.4594594594594594,
"grad_norm": 14.000101089477539,
"learning_rate": 2.9041487839771104e-05,
"loss": 3.0297,
"step": 378
},
{
"epoch": 1.4826254826254825,
"grad_norm": 15.382340431213379,
"learning_rate": 2.8612303290414884e-05,
"loss": 3.7875,
"step": 384
},
{
"epoch": 1.505791505791506,
"grad_norm": 12.228459358215332,
"learning_rate": 2.8183118741058657e-05,
"loss": 3.8071,
"step": 390
},
{
"epoch": 1.528957528957529,
"grad_norm": 12.940893173217773,
"learning_rate": 2.7753934191702436e-05,
"loss": 2.9065,
"step": 396
},
{
"epoch": 1.5521235521235521,
"grad_norm": 16.97939682006836,
"learning_rate": 2.732474964234621e-05,
"loss": 3.2808,
"step": 402
},
{
"epoch": 1.5752895752895753,
"grad_norm": 17.717403411865234,
"learning_rate": 2.689556509298999e-05,
"loss": 3.4982,
"step": 408
},
{
"epoch": 1.5984555984555984,
"grad_norm": 8.225591659545898,
"learning_rate": 2.6466380543633762e-05,
"loss": 3.6047,
"step": 414
},
{
"epoch": 1.6216216216216215,
"grad_norm": 11.827160835266113,
"learning_rate": 2.603719599427754e-05,
"loss": 3.219,
"step": 420
},
{
"epoch": 1.6447876447876448,
"grad_norm": 14.637051582336426,
"learning_rate": 2.5608011444921314e-05,
"loss": 3.7435,
"step": 426
},
{
"epoch": 1.667953667953668,
"grad_norm": 7.794189453125,
"learning_rate": 2.5178826895565094e-05,
"loss": 3.4536,
"step": 432
},
{
"epoch": 1.691119691119691,
"grad_norm": 14.05357837677002,
"learning_rate": 2.474964234620887e-05,
"loss": 3.2552,
"step": 438
},
{
"epoch": 1.7142857142857144,
"grad_norm": 9.823927879333496,
"learning_rate": 2.4320457796852646e-05,
"loss": 3.4115,
"step": 444
},
{
"epoch": 1.7374517374517375,
"grad_norm": 45.474586486816406,
"learning_rate": 2.3891273247496423e-05,
"loss": 3.3538,
"step": 450
},
{
"epoch": 1.7606177606177607,
"grad_norm": 23.240049362182617,
"learning_rate": 2.3462088698140202e-05,
"loss": 3.5271,
"step": 456
},
{
"epoch": 1.7837837837837838,
"grad_norm": 13.07448959350586,
"learning_rate": 2.303290414878398e-05,
"loss": 3.6199,
"step": 462
},
{
"epoch": 1.806949806949807,
"grad_norm": 14.969829559326172,
"learning_rate": 2.2603719599427755e-05,
"loss": 4.2248,
"step": 468
},
{
"epoch": 1.83011583011583,
"grad_norm": 11.915005683898926,
"learning_rate": 2.217453505007153e-05,
"loss": 3.6249,
"step": 474
},
{
"epoch": 1.8532818532818531,
"grad_norm": 14.839444160461426,
"learning_rate": 2.1745350500715307e-05,
"loss": 3.214,
"step": 480
},
{
"epoch": 1.8764478764478765,
"grad_norm": 12.58840274810791,
"learning_rate": 2.1316165951359084e-05,
"loss": 3.0665,
"step": 486
},
{
"epoch": 1.8996138996138996,
"grad_norm": 14.892538070678711,
"learning_rate": 2.0886981402002863e-05,
"loss": 3.6376,
"step": 492
},
{
"epoch": 1.922779922779923,
"grad_norm": 8.315190315246582,
"learning_rate": 2.045779685264664e-05,
"loss": 2.5824,
"step": 498
},
{
"epoch": 1.945945945945946,
"grad_norm": 12.847142219543457,
"learning_rate": 2.0028612303290416e-05,
"loss": 2.5557,
"step": 504
},
{
"epoch": 1.9691119691119692,
"grad_norm": 11.103631019592285,
"learning_rate": 1.9599427753934195e-05,
"loss": 3.4455,
"step": 510
},
{
"epoch": 1.9922779922779923,
"grad_norm": 11.917842864990234,
"learning_rate": 1.917024320457797e-05,
"loss": 3.6309,
"step": 516
},
{
"epoch": 2.0,
"eval_gen_len": 6.1077,
"eval_loss": 3.2486257553100586,
"eval_rouge1": 9.7128,
"eval_rouge2": 5.6141,
"eval_rougeL": 9.3222,
"eval_rougeLsum": 9.4984,
"eval_runtime": 4.6056,
"eval_samples_per_second": 14.113,
"eval_steps_per_second": 3.691,
"step": 518
},
{
"epoch": 2.0154440154440154,
"grad_norm": 5.787186622619629,
"learning_rate": 1.8741058655221748e-05,
"loss": 3.2913,
"step": 522
},
{
"epoch": 2.0386100386100385,
"grad_norm": 10.957201957702637,
"learning_rate": 1.8311874105865524e-05,
"loss": 2.195,
"step": 528
},
{
"epoch": 2.0617760617760617,
"grad_norm": 11.480974197387695,
"learning_rate": 1.78826895565093e-05,
"loss": 2.8584,
"step": 534
},
{
"epoch": 2.0849420849420848,
"grad_norm": 9.375560760498047,
"learning_rate": 1.7453505007153077e-05,
"loss": 3.2412,
"step": 540
},
{
"epoch": 2.108108108108108,
"grad_norm": 11.552406311035156,
"learning_rate": 1.7024320457796853e-05,
"loss": 2.9892,
"step": 546
},
{
"epoch": 2.1312741312741315,
"grad_norm": 8.1609468460083,
"learning_rate": 1.6595135908440632e-05,
"loss": 3.3593,
"step": 552
},
{
"epoch": 2.1544401544401546,
"grad_norm": 11.221341133117676,
"learning_rate": 1.616595135908441e-05,
"loss": 2.9685,
"step": 558
},
{
"epoch": 2.1776061776061777,
"grad_norm": 10.078996658325195,
"learning_rate": 1.5736766809728185e-05,
"loss": 2.7808,
"step": 564
},
{
"epoch": 2.200772200772201,
"grad_norm": 10.252344131469727,
"learning_rate": 1.530758226037196e-05,
"loss": 3.3327,
"step": 570
},
{
"epoch": 2.223938223938224,
"grad_norm": 13.17142391204834,
"learning_rate": 1.4878397711015737e-05,
"loss": 3.4719,
"step": 576
},
{
"epoch": 2.247104247104247,
"grad_norm": 13.214423179626465,
"learning_rate": 1.4449213161659514e-05,
"loss": 3.1222,
"step": 582
},
{
"epoch": 2.27027027027027,
"grad_norm": 10.087789535522461,
"learning_rate": 1.402002861230329e-05,
"loss": 2.5103,
"step": 588
},
{
"epoch": 2.2934362934362933,
"grad_norm": 12.04149055480957,
"learning_rate": 1.3590844062947066e-05,
"loss": 3.4174,
"step": 594
},
{
"epoch": 2.3166023166023164,
"grad_norm": 12.798707962036133,
"learning_rate": 1.3161659513590846e-05,
"loss": 3.4742,
"step": 600
},
{
"epoch": 2.33976833976834,
"grad_norm": 13.191904067993164,
"learning_rate": 1.2732474964234622e-05,
"loss": 3.3361,
"step": 606
},
{
"epoch": 2.362934362934363,
"grad_norm": 11.446030616760254,
"learning_rate": 1.2303290414878398e-05,
"loss": 2.8801,
"step": 612
},
{
"epoch": 2.386100386100386,
"grad_norm": 9.028064727783203,
"learning_rate": 1.1874105865522175e-05,
"loss": 2.5872,
"step": 618
},
{
"epoch": 2.4092664092664093,
"grad_norm": 11.909852981567383,
"learning_rate": 1.1444921316165953e-05,
"loss": 2.9751,
"step": 624
},
{
"epoch": 2.4324324324324325,
"grad_norm": 11.196946144104004,
"learning_rate": 1.1015736766809729e-05,
"loss": 2.6607,
"step": 630
},
{
"epoch": 2.4555984555984556,
"grad_norm": 6.7401442527771,
"learning_rate": 1.0586552217453507e-05,
"loss": 2.9422,
"step": 636
},
{
"epoch": 2.4787644787644787,
"grad_norm": 9.36950969696045,
"learning_rate": 1.0157367668097283e-05,
"loss": 3.5546,
"step": 642
},
{
"epoch": 2.501930501930502,
"grad_norm": 16.527103424072266,
"learning_rate": 9.72818311874106e-06,
"loss": 2.3793,
"step": 648
},
{
"epoch": 2.525096525096525,
"grad_norm": 7.8193135261535645,
"learning_rate": 9.298998569384835e-06,
"loss": 2.8579,
"step": 654
},
{
"epoch": 2.5482625482625485,
"grad_norm": 12.883255004882812,
"learning_rate": 8.869814020028613e-06,
"loss": 2.817,
"step": 660
},
{
"epoch": 2.571428571428571,
"grad_norm": 10.683404922485352,
"learning_rate": 8.44062947067239e-06,
"loss": 2.8759,
"step": 666
},
{
"epoch": 2.5945945945945947,
"grad_norm": 8.476865768432617,
"learning_rate": 8.011444921316166e-06,
"loss": 3.5438,
"step": 672
},
{
"epoch": 2.617760617760618,
"grad_norm": 16.314342498779297,
"learning_rate": 7.582260371959943e-06,
"loss": 3.4169,
"step": 678
},
{
"epoch": 2.640926640926641,
"grad_norm": 14.487051963806152,
"learning_rate": 7.153075822603721e-06,
"loss": 3.4511,
"step": 684
},
{
"epoch": 2.664092664092664,
"grad_norm": 13.450141906738281,
"learning_rate": 6.723891273247497e-06,
"loss": 2.8801,
"step": 690
},
{
"epoch": 2.687258687258687,
"grad_norm": 14.612557411193848,
"learning_rate": 6.2947067238912735e-06,
"loss": 2.6347,
"step": 696
},
{
"epoch": 2.7104247104247103,
"grad_norm": 11.321943283081055,
"learning_rate": 5.8655221745350506e-06,
"loss": 2.8296,
"step": 702
},
{
"epoch": 2.7335907335907335,
"grad_norm": 18.955806732177734,
"learning_rate": 5.436337625178827e-06,
"loss": 3.0904,
"step": 708
},
{
"epoch": 2.756756756756757,
"grad_norm": 6.251610279083252,
"learning_rate": 5.007153075822604e-06,
"loss": 2.2731,
"step": 714
},
{
"epoch": 2.7799227799227797,
"grad_norm": 8.317915916442871,
"learning_rate": 4.577968526466381e-06,
"loss": 2.6778,
"step": 720
},
{
"epoch": 2.8030888030888033,
"grad_norm": 12.207304000854492,
"learning_rate": 4.148783977110158e-06,
"loss": 3.3065,
"step": 726
},
{
"epoch": 2.8262548262548264,
"grad_norm": 16.136972427368164,
"learning_rate": 3.7195994277539344e-06,
"loss": 3.9406,
"step": 732
},
{
"epoch": 2.8494208494208495,
"grad_norm": 13.954407691955566,
"learning_rate": 3.2904148783977115e-06,
"loss": 2.9646,
"step": 738
},
{
"epoch": 2.8725868725868726,
"grad_norm": 12.064271926879883,
"learning_rate": 2.861230329041488e-06,
"loss": 3.1461,
"step": 744
},
{
"epoch": 2.8957528957528957,
"grad_norm": 11.247983932495117,
"learning_rate": 2.432045779685265e-06,
"loss": 3.4405,
"step": 750
},
{
"epoch": 2.918918918918919,
"grad_norm": 8.756580352783203,
"learning_rate": 2.0028612303290415e-06,
"loss": 3.6948,
"step": 756
},
{
"epoch": 2.942084942084942,
"grad_norm": 10.008057594299316,
"learning_rate": 1.5736766809728184e-06,
"loss": 3.2626,
"step": 762
},
{
"epoch": 2.965250965250965,
"grad_norm": 5.3783650398254395,
"learning_rate": 1.1444921316165953e-06,
"loss": 2.7083,
"step": 768
},
{
"epoch": 2.988416988416988,
"grad_norm": 8.535452842712402,
"learning_rate": 7.15307582260372e-07,
"loss": 3.0117,
"step": 774
},
{
"epoch": 3.0,
"eval_gen_len": 6.0615,
"eval_loss": 3.1822056770324707,
"eval_rouge1": 9.5428,
"eval_rouge2": 5.4799,
"eval_rougeL": 9.1926,
"eval_rougeLsum": 9.3965,
"eval_runtime": 4.675,
"eval_samples_per_second": 13.904,
"eval_steps_per_second": 3.636,
"step": 777
}
],
"logging_steps": 6,
"max_steps": 777,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 18382916321280.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}